Learning region-guided scale-aware feature selection for object detection | |
Liu, Liu1,2; Wang, Rujing1; Xie, Chengjun1; Li, Rui1; Wang, Fangyuan1,2; Zhou, Man1,2; Teng, Yue1,2 | |
刊名 | NEURAL COMPUTING & APPLICATIONS |
2020-10-10 | |
关键词 | Scale variation Object detection RoI Pyramid Scale-aware feature selective |
ISSN号 | 0941-0643 |
DOI | 10.1007/s00521-020-05400-w |
通讯作者 | Wang, Rujing(rjwang@iim.ac.cn) |
英文摘要 | Scale variation is one of the major challenges in object detection task. Modern region-based object detection architectures often adopt Feature Pyramid Network (FPN) as feature extraction neck to achieve multi-scale feature representation in solving scale variation problem. However, due to the rough feature selection strategy in Region of Interest (RoI) feature extraction step, these methods might not perform well on object detection under strong scale variation. In this work, we are motivated by the limitations of current FPN-based two-stage object detectors and then present a novel module, namely scale-aware feature selective (SAFS) module, that flexibly and adaptively selects feature levels in two-stage object detectors. Specifically, we firstly build the RoI Pyramid in standard FPN structure to extract RoI features from various scale levels. Next, in order to achieve scale-aware mechanism for solving scale variation issue, we develop a novel weighting gate function containing one set of trainable parameters to automatically learn the fusion weight for each RoI feature level, which relieves the limitation of hard feature selection strategy guided by online instance size. Outputs from the RoI features with the learned weights are fused for classification and bounding box regression. Furthermore, we design a multi-level SAFS architecture to obtain different types of RoI feature combinations that ensures our method is more robust to various instance scales. Experimental results show that our SAFS module is very compatible with most of two-stage object detectors and could achieve state-of-the-art results with Average Precision of 48.3 on COCOtest-devand other popular object detection benchmarks. Our code will be made publicly available. |
资助项目 | National Natural Science Foundation of China (NSFC)[61773360] ; National Natural Science Foundation of China (NSFC)[31671586] ; Major Special Science and Technology Project of Anhui Province[201903a06020006] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | SPRINGER LONDON LTD |
WOS记录号 | WOS:000578592700001 |
资助机构 | National Natural Science Foundation of China (NSFC) ; Major Special Science and Technology Project of Anhui Province |
内容类型 | 期刊论文 |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/104675] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Wang, Rujing |
作者单位 | 1.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China 2.Univ Sci & Technol China, Hefei 230026, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Liu,Wang, Rujing,Xie, Chengjun,et al. Learning region-guided scale-aware feature selection for object detection[J]. NEURAL COMPUTING & APPLICATIONS,2020. |
APA | Liu, Liu.,Wang, Rujing.,Xie, Chengjun.,Li, Rui.,Wang, Fangyuan.,...&Teng, Yue.(2020).Learning region-guided scale-aware feature selection for object detection.NEURAL COMPUTING & APPLICATIONS. |
MLA | Liu, Liu,et al."Learning region-guided scale-aware feature selection for object detection".NEURAL COMPUTING & APPLICATIONS (2020). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论